aboutsummaryrefslogtreecommitdiffstats
path: root/modules/sd_models.py
AgeCommit message (Collapse)AuthorLines
2023-08-23set devices.dtype_unet correctlyAUTOMATIC1111-1/+2
2023-08-22add --medvram-sdxlAUTOMATIC1111-8/+8
2023-08-21Fix for consistency with shared.opts.sd_vae of UIUminosachi-0/+1
2023-08-20Change where VAE state are stored in modelUminosachi-2/+0
2023-08-20Change to access sd_model attribute with dotUminosachi-2/+2
2023-08-20Store base_vae and loaded_vae_file in sd_modelUminosachi-16/+8
2023-08-20Fix SD VAE switch error after model reuseUminosachi-2/+20
2023-08-17resolve the issue with loading fp16 checkpoints while using --no-halfAUTOMATIC1111-1/+4
2023-08-16send weights to target device instead of CPU memoryAUTOMATIC1111-1/+16
2023-08-16Revert "send weights to target device instead of CPU memory"AUTOMATIC1111-1/+1
This reverts commit 0815c45bcdec0a2e5c60bdd5b33d95813d799c01.
2023-08-16send weights to target device instead of CPU memoryAUTOMATIC1111-1/+1
2023-08-12put refiner into main UI, into the new accordions sectionAUTOMATIC1111-0/+3
add VAE from main model into infotext, not from refiner model option to make scripts UI without gr.Group fix inconsistencies with refiner when usings samplers that do more denoising than steps
2023-08-10resolve merge issuesAUTOMATIC1111-2/+5
2023-08-10Merge branch 'dev' into refinerAUTOMATIC1111-11/+12
2023-08-09fix checkpoint name jumping around in the list of checkpoints for no good reasonAUTOMATIC1111-3/+9
2023-08-09Merge pull request #12426 from AUTOMATIC1111/split_sharedAUTOMATIC1111-8/+1
Split shared.py into multiple files
2023-08-09split shared.py into multiple files; should resolve all circular reference ↵AUTOMATIC1111-8/+1
import errors related to shared.py
2023-08-08Merge branch 'dev' into refinerAUTOMATIC1111-1/+2
2023-08-08Fix mismatch between shared.sd_model & shared.optsUminosachi-0/+2
2023-08-07apply unet overrides after switching modelAUTOMATIC1111-0/+1
2023-08-07SD VAE rework 2AUTOMATIC1111-1/+1
- the setting for preferring opts.sd_vae has been inverted and reworded - resolve_vae function made easier to read and now returns an object rather than a tuple - if the checkbox for overriding per-model preferences is checked, opts.sd_vae overrides checkpoint user metadata - changing VAE in user metadata for currently loaded model immediately applies the selection
2023-08-06initial refiner supportAUTOMATIC1111-1/+17
2023-08-05Merge branch 'dev' into multiple_loaded_modelsAUTOMATIC1111-12/+17
2023-08-05Merge pull request #12181 from AUTOMATIC1111/hires_checkpointAUTOMATIC1111-10/+17
Hires fix change checkpoint
2023-08-04fix: prevent cache model.state_dict() after model hijackAnyISalIn-2/+3
Signed-off-by: AnyISalIn <anyisalin@gmail.com>
2023-08-03add style editor dialogAUTOMATIC1111-1/+1
rework toprow for img2img and txt2img to use a class with fields fix the console error when editing checkpoint user metadata
2023-08-01repair merge errorAUTOMATIC1111-1/+0
2023-08-01Merge branch 'dev' into multiple_loaded_modelsAUTOMATIC1111-11/+18
2023-08-01add metadata to checkpoint mergerAUTOMATIC1111-1/+1
2023-08-01show metadata for SD checkpoints in the extra networks UIAUTOMATIC1111-10/+16
2023-08-01option to keep multiple models in memoryAUTOMATIC1111-24/+112
2023-07-31additional memory improvements when switching between models of different typesAUTOMATIC1111-1/+4
2023-07-30hires fix checkpoint selectionAUTOMATIC1111-9/+13
2023-07-24Use less RAM when creating modelsAUTOMATIC1111-6/+10
2023-07-18fix the issue with /sdapi/v1/options failing (this time for sure!)AUTOMATIC1111-1/+1
fix automated tests downloading CLIP model
2023-07-18Add support for `--upcast-sampling` with SD XLbrkirch-1/+1
2023-07-17hide cards for networks of incompatible stable diffusion version in Lora ↵AUTOMATIC1111-0/+3
extra networks interface
2023-07-14linterAUTOMATIC1111-1/+1
2023-07-14initial SDXL refiner supportAUTOMATIC1111-1/+2
2023-07-13add support for SDXL loras with te1/te2 modulesAUTOMATIC1111-1/+2
2023-07-13repair --no-half for SDXLAUTOMATIC1111-4/+5
2023-07-12SDXL supportAUTOMATIC1111-2/+12
2023-07-11getting SD2.1 to run on SDXL repoAUTOMATIC1111-2/+6
2023-07-08Fix typo: checkpoint_alisasesAarni Koskela-5/+6
2023-07-08added torch.mps.empty_cache() to torch_gc()AUTOMATIC1111-1/+0
changed a bunch of places that use torch.cuda.empty_cache() to use torch_gc() instead
2023-06-27send tensors to the correct device when loading from safetensors file with ↵AUTOMATIC-1/+3
memmap disabled for #11260
2023-06-27Merge pull request #11260 from dhwz/devAUTOMATIC1111-2/+5
fix very slow loading speed of .safetensors files
2023-06-16fix very slow loading speed of .safetensors filesdhwz-2/+5
2023-06-13Use os.makedirs(..., exist_ok=True)Aarni Koskela-2/+1
2023-06-01assign devices.dtype early because it's needed before the model is loadedAUTOMATIC-2/+0
generated by cgit v1.2.3 (git 2.39.1) at 2025-10-07 19:29:28 +0000